Embedding Learning on Spectral–Spatial Graph for Semisupervised Hyperspectral Image Classification
Embedding Learning on Spectral–Spatial Graph for Semisupervised Hyperspectral Image Classification
复制标题
DOI：
10.1109/lgrs.2017.2737020
复制
发表时间：
2017-10
影响因子：
4.8
通讯作者：
Jiayan Cao;Bin Wang-
中科院分区：
文献类型：
--
作者：
Jiayan Cao;Bin Wang-
在实际应用中，标注数据的成本和时间都非常昂贵，标注样本的稀缺性是高光谱图像分类任务的主要障碍。为了缓解由于缺乏训练数据而可能发生的任何欠拟合问题，半监督分类框架探索未标记样本的内在信息，并桥接标记和未标记数据。在这封信中，我们提出了一个新的框架，同时学习底层流形表示和半监督分类器。该算法避免了显式的特征向量分解，直接通过在相似图上迭代随机游走进行采样，使得算法在大型图上的实现成为可能。为了验证嵌入学习过程的有效性，我们将所提出的方法与其他降维和基于流形学习的方法进行了比较。实验结果表明，与传统的半监督策略相比，图嵌入方法具有更好的效果。
Scarcity of labeled samples is the main obstacle for hyperspectral image classification tasks when labeling data is considerably costly and time-consuming in real-world scenarios. To alleviate any underfitting problem that may occur due to lack of training data, semisupervised classification frameworks explore the intrinsic information of unlabeled samples and bridge labeled and unlabeled data. In this letter, we propose a novel framework that learns underlying manifold representation and semisupervised classifier simultaneously. It avoids explicit eigenvector decomposition and directly samples via iterating random walk on the similarity graph, which makes it feasible to implement on huge graphs. To verify the efficacy of embedding the learning process, we compare the proposed method with other dimensionality reduction and manifold-learning-based approaches. Experimental results show that compared to the methods using traditional semisupervised strategies, the graph embedding method gives a better result.